Prompt Cache as Covert Channel: TTFT Probing Leaks Cross-Tenant Prompts
Prompt caching saves 80–90% on cached requests by sharing KV state across tenants — and turns time-to-first-token into a side channel that recovers other customers' prompts at 92% accuracy. The cost-vs-isolation trade-off most teams have not had.
insider
ai-security
llm-infrastructure
multi-tenancy
+2